© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9619
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to medical case studies and reports, particularly diagnoses and treatments

    oai_token-act-pair · gemini-2.0-flash

    medical case reports

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.50
    BASEPATH
    -0.50
    ngths
    -0.49
    quartered
    -0.49
     angekommen
    -0.48
     rumahnya
    -0.48
     parkir
    -0.48
    dampak
    -0.47
     xmlns
    -0.47
     oscuros
    -0.47
    POSITIVE LOGITS
    Geografie
    0.60
    ))))))))
    0.59
    estacks
    0.59
    CodedInputStream
    0.56
    الإنجليزية
    0.54
    EDEFAULT
    0.54
    ucha
    0.53
    tagHelperRunner
    0.53
     />);
    0.53
     meningitis
    0.51
    Activations Density 13.416%

    No Known Activations